make-dogfood

make-dogfood is a command for Claude Code from athola/claude-night-market. It costs 18 tokens per session (1,599 once invoked), scanned A, original, MIT.

A command for checking Makefiles, the files that define repeatable project commands, and identifying or generating missing targets.

In plain words
What is it for?
Use it to analyze plugin Makefiles, test target coverage, generate missing targets, create Makefiles where needed, or apply reviewed changes with a dry run first.
Why use it?
It reveals gaps in build and maintenance commands and lets you preview proposed additions before changing files.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 plugins/abstract/scripts/makefile_dogfooder.py --mode analyze.

Part of the abstract plugin — 16 skills, 17 commands, 5 agents, 4 hooks shipped together

Good fit Use it to analyze plugin Makefiles, test target coverage, generate missing targets, create Makefiles where needed, or apply reviewed changes with a dry run first.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market
agentmods
npx agentmods add commands/athola/claude-night-market/make-dogfood

Made for: Claude Code.

Or install abstract, the plugin that ships this one along with the rest of its 16 skills, 17 commands, 5 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for make-dogfood

README.md
[![agentmods](https://agentmods.dev/badge/commands/athola/claude-night-market/make-dogfood/github.svg)](https://agentmods.dev/commands/athola/claude-night-market/make-dogfood)
Your own site
<a href="https://agentmods.dev/commands/athola/claude-night-market/make-dogfood"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/make-dogfood/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for make-dogfood

Your own site · 80×15
<a href="https://agentmods.dev/commands/athola/claude-night-market/make-dogfood"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/make-dogfood.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,599 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.01599
Opus 5 $0.00009 $0.00800
Sonnet 5 $0.00004 $0.00320
Haiku 4.5 $0.00002 $0.00160

Measured 12d ago against content hash f7dcc73eb1d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

make-dogfood scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/abstract/commands/make-dogfood.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Makefile Dogfooding Command

Use the makefile-dogfooder script to analyze, test, and enhance Makefiles across the claude-night-market project with thorough safety checks and auto-generation capabilities.

When To Use

Use this command when you need to:

  • Analyzing Makefile completeness
  • Testing existing make targets
  • Generating missing targets
  • Preparing plugins for release
  • Auditing Makefile coverage across plugins
  • Creating Makefiles for plugins without them

When NOT To Use

Avoid this command if:

  • Writing initial Makefiles from scratch (use --generate-makefiles instead)
  • Debugging specific build failures
  • Creating custom build systems

Parameters

  • --mode: Operation mode (default: analyze)

    • analyze: Only analyze and report gaps (SAFE - no changes)
    • generate: Show generated targets without writing files
    • apply: Write targets to Makefiles (use with --dry-run first)
  • --plugin: Restrict to specific plugin (e.g., --plugin sanctum)

    • Recommended: Test on one plugin before applying to all
  • --dry-run: Preview changes without writing files (HIGHLY RECOMMENDED)

    • Always use this before applying changes for real
    • Shows what will be generated/modified
  • --generate-makefiles: Generate Makefiles for plugins that don't have them

    • Follows attune:makefile-generation pattern
    • Auto-detects language (Python/Rust/TypeScript)
    • Creates standard targets for detected language
  • --preflight-check: Run validation checks before processing

    • Validates directories exist
    • Checks write permissions
    • Detects git repository for rollback
  • --verbose: Show detailed progress and error messages

  • --output: Output format (text|json, default: text)

Workflow

1. Discovery Phase

Scan all Makefiles and build an inventory of existing targets:

  • Find all Makefile and .mk files
  • Extract target definitions and metadata
  • Build dependency graphs
  • Identify plugin type (leaf vs aggregator)

2. Analysis Phase

Evaluate Makefiles against best practices:

  • Check for essential targets (help, clean, test, lint)
  • Identify missing convenience targets (demo, quick-run)
  • Detect anti-patterns and inconsistencies
  • Score each Makefile on completeness (0-100)

Read the full file on GitHub · 199 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 199 lines · 18 tokens per session scan A f7dcc73eb1d1

Subscribe to this mod's changes

make-dogfood is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 1,599 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.